kvb-git-commit-no-verify, kvb-git-commit-next and kvb-skill-essence printed the full staged diff into the chat before every commit or batch write. The operator ordered on 2026-11-11 that the chat shows only the diff stat and the score table, to save tokens. 🎯 Fix: 92 % 💥 Break: 2 % 💸 Cost: 99 % ⏱️ Time: 100 % 🛡️ Security: 100 % 🏆 Score: 91 🚦 Gate: ✅ 90/5, cost and time <= 100, security 100 % Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
3.4 KiB
3.4 KiB
name, description
| name | description |
|---|---|
| kvb-git-commit-next | Search every branch for the staged fix, commit it with --no-verify, then stage and brief the next bundle. |
- Describe the staged bundle in one line, so a wrong search intent is
visible. Then
git fetch --all --prune --tagsand hunt the staged fix across every ref with the kvb-git-merge-fix skill'sfind_fix.py(by--grep, by-S, by--path). Only the search runs here: never cherry-pick or merge, never touch the staging index or the tree. - A similar fix on another branch is a stop: run the kvb-think-dialectic skill on the two candidates (staged version as thesis, foreign commit as antithesis) until one survives, then present sha, branch, both diff stats, the verdict and the recommended move (keep staged / take theirs / combine). Wait for the operator's decision; do not commit.
- Nothing similar found, or the operator picked the staged version: run the
kvb-git-commit-no-verify skill on the currently staged changes
(kvb-code-clean pass and kvb-check-legal check first, then the
kvb-check-score commit table of 📁 worktree,
🌿 branch, 📊 diff stat, scores with 🛡️ security and gate, then
git commit --no-verify, exact staging index only, its message carrying thescore.py --message-blockparagraph right before theCo-Authored-Byline as one-margument, then the table again with the hash). Its approval-prompt duty is binding: the commit call's approval prompt names worktree, branch, diff stat and the score values with 🛡️ security, and the message holds the block, or the call is not sent. Gate exit 4 (critical security finding): no commit, the call is never sent. Exit 1 is shown and the operator's word decides; exit 3 asks the operator again first, naming each cause. - Group the remaining uncommitted changes into logical bundles (one concern
per bundle: same failure class, mechanism or role) and stage the next one;
never mix concerns to save a commit. Staging happens here and nowhere
else: never stage merely to run a lint or a test. Checks that enumerate
through
git ls-filesalready see tracked, modified files and read the worktree; only an untracked NEW file needsgit addto become visible. Path-scope everygit addto the bundle:git add -Asweeps up the operator's own edits and local config. A file that carries two bundles is staged by line:${CLAUDE_SKILL_DIR}/scripts/stage_hunks.py --repo <worktree> --file <path> --match <regex>, first with--dry-run. - For the newly staged bundle run the kvb-code-clean pass, then the
kvb-think-explain skill (what the changes do and how the pieces
interact, file:line-anchored), then the kvb-check-confidence skill (its
kvb-check-score block with 🛡️ security from
security.pyof kvb-check-security, evidence, residuals). - Close with the staged bundle's commit table (
score.py ... --commit-table <worktree>: 📁 worktree, 🌿 branch, 📊 diff stat, scores, gate), what remains unstaged, and wait for the operator's commit decision; never auto-commit the newly staged bundle. Ask through the kvb-git-diff skill: a hub approval is the operator's commit decision for that one bundle only once itsapproval.py verifystep exits 0 on the exact staged tree; otherwise the chat question stays the fallback. A gate exit 4 says up front that the bundle cannot be committed until its critical finding is fixed.